Every mod, cheapest first

Ranked by what a mod adds to every session before you have asked anything; equal costs break by stars gained this week, so the near-free mods people are picking up right now lead. A zero is real — a rule with globs costs nothing until a file matches — and everything else is a number you can check against the source.

#ModTypeTokens / sessionThis weekStarsScanRating
101 dedupeVectifyAI/PageIndexYou are a GitHub issue deduplication assistant. Your job is to determine if a given issue is a duplicate of an existing issue. Command 0 until used 35k A
102 api-updateComposioHQ/composioCheck for open PRs in the Composio client repositories and create a plan for updating the SDKs. Command 0 until used 30k A
103 connect-clients-syncComposioHQ/composioSyncs AI client definitions from the dashboard repo (ComposioHQ/composiodashboard) to the Composio Connect docs page. Agent 0 until used 30k A
104 tool-prompt-optimizationcan1357/oh-my-piOptimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool… Skill 0 until used 28k A
105 issue-intelligence-analystEveryInc/compound-engineering-pluginNote: The current year is 2026. Use this when evaluating issue recency and trends. Agent 0 until used 25k A
106 learnings-researcherEveryInc/compound-engineering-pluginYou are a domain-agnostic institutional knowledge researcher. Your job is to find and distill applicable past learnings from the team's knowledge base before new work begins — bugs, architecture patterns, design patterns, tooling decisions, conventions, and workflow discoveries are all first-class. Your work helps… Agent 0 until used 25k A
107 docs-reviewerComposioHQ/composioReviews documentation PRs for Composio, an SDK that connects AI agents to external tools and APIs. Agent 0 until used 30k A
108 fix-issuescan1357/oh-my-piDiagnose, reproduce, then fix reproducible open GitHub issues in parallel: one clean worktree/issue; symlink build artifacts to avoid rebuilds. Command 0 until used 28k A
109 review-prscan1357/oh-my-piParallel PR triage: decide merge-worthiness, prepare rebased worktrees, fix blockers, return them for human merge. Command 0 until used 28k A
110 askYeachan-Heo/oh-my-claudecodeThis compatibility command keeps /oh-my-claudecode:ask available without loading the full ask skill description in every Claude Code session. Command 0 until used 39k A
111 READMEalirezarezvani/claude-skillsGit workflow and quality assurance commands for the claude-skills repository. Command 0 until used 25k A
112 pr-conventionspromptfoo/promptfooPR titles follow Conventional Commits format. They become squash-merge commit messages and changelog entries. Agent 0 until used 25k A
113 devbox-entrypointcontinuedev/continueContext: runloop resumes a devbox by re-running the same entrypoint script, which invokes cn serve --id .... Because the entrypoint always replays, the CLI must avoid duplicating state on restart. Command 0 until used 36k A
114 changelogComposioHQ/composioCheck the changes between the current branch and next branch, and create a changelog file inside /docs/content/changelog in the file format of MM-DD-YY- .mdx. Command 0 until used 30k A
115 claude-code-guideasgeirtj/system_prompts_leaksYou are the Claude guide agent. Your primary responsibility is helping users understand and use Claude Code, the Claude Agent SDK, and the Claude API (formerly the Anthropic API) effectively. Agent 0 until used 64k A
116 compactasgeirtj/system_prompts_leaksCRITICAL: Respond with TEXT ONLY. Do NOT call any tools. Command 0 until used 64k A
117 design-reviewnextlevelbuilder/ui-ux-pro-max-skillRun the 7-phase design review (WCAG AA, responsive, interaction) on a page or URL. Command 0 until used 123k A
118 fill-model-descriptionsmarimo-team/marimoFill empty description: "" fields in packages/llm-info/data/models.yml by querying OpenRouter and provider documentation. Use when the user asks to populate model descriptions, enrich the model catalog, or backfill descriptions after running pnpm sync-models. Skill 0 until used 23k A
119 agent_typesmicrosoft/UFOThis document describes how the unified three-layer Device Agent architecture is implemented across different platforms. While the core framework (State, Processor, Command layers) remains consistent, each platform implements specialized agents optimized for their native control mechanisms and hierarchies.… Agent 0 until used 9.6k A
120 coding-guidelinestrpc/trpcYou are working on tRPC - a TypeScript-first RPC library that provides end-to-end type safety between client and server. As a TypeScript expert contributing to this library, you should. Cursor rule 0 until used 41k A
121 i18n-translatorslopus/happyUse this agent when you need to add new translatable strings to the application or verify existing translations. This includes: adding new UI text that needs to be translated, ensuring translations are consistent across all language files, verifying that translations fit the UI context (headers, buttons, multiline… Agent 0 until used 24k A
122 overviewmicrosoft/UFODevice Agents are the execution engines of UFO3's multi-device orchestration system. Each device agent operates as an autonomous, intelligent controller that translates high-level user intentions into low-level system commands. The architecture is designed for extensibility, safety, and scalability across… Agent 0 until used 9.6k A
123 upgrade-teststrpc/trpc// ✅ CORRECT: Upgrade package pattern await using ctx = testReactResource(appRouter, { server: { // server configuration }, client(opts) { return { links: [ httpLink({ url: opts.httpUrl, // client configuration }), ], }; }, }). Cursor rule 0 until used 41k A
124 AGENTSpromptfoo/promptfooCommander.js-based CLI commands registered in src/main.ts. Command 0 until used 25k A
125 MIGRATE_DESIGNelizaOS/elizaDesign doc for the migration tool PR. Author: Sol ([email protected]). Co-authored-by: wakesync. Command 0 until used 19k A
126 chat-agentscloudflare/agentsBuild AI-powered chat interfaces with AIChatAgent and useAgentChat. Messages are automatically persisted to SQLite, streams resume on disconnect, and tool calls work across server and client. Agent 0 until used 5.5k A
127 DEPLOY_DESIGNelizaOS/elizaStatus: implemented trigger path. The CLI queues cloud deployments, can attach a custom domain, and polls public deployment status. Local build/upload, first-run credential prompting, deploy logs, and watch mode remain follow-up boundaries. Command 0 until used 19k A
128 drizzletriggerdotdev/trigger.devUse this skill when writing or modifying Drizzle ORM schemas, queries, or migrations in this repo — specifically the @internal/dashboard-agent-db package (the dashboard agent's conversation datastore). Covers pg-core schema definition, the postgres-js driver, drizzle-kit migrations, and this repo's conventions: a… Skill 0 until used 16k A
129 sessionscloudflare/agentsThe Session API provides persistent conversation storage for agents, with tree-structured messages, context blocks, compaction, full-text search, and AI-controllable tools. By default it uses Durable Object SQLite; external Postgres storage is also available for apps that need shared database access, analytics, or… Agent 0 until used 5.5k A
130 hunt-sentry-issuescompiler-explorer/compiler-explorerI need you to help me systematically hunt and fix Sentry issues. Command 0 until used 19k A
131 directorheygen-com/hyperframesTurn a request into a shot-plan.json for a short (3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md. Agent 0 until used 43k A
132 open-code-reviewalibaba/open-code-reviewInvoke the professional code review Agent CLI tool OpenCodeReview (OCR) to review current code changes, and let the Agent autonomously decide whether to apply fixes. Command 0 until used 22k A
133 new_model_supportaxolotl-ai-cloud/axolotlGuide for debugging and adding support for new model architectures in axolotl. Based on lessons learned from Gemma4, Gemma3, Qwen2-VL, and other multimodal/MoE models. Agent 0 until used 12k A
134 Meshery Docs Contributormeshery/mesheryExpert-level documentation agent specialized in contributing to Meshery's Hugo-based documentation site with deep knowledge of technical writing, information architecture, Markdown, Hugo templates, shortcodes, partials, and the Meshery ecosystem. Agent 0 until used 12k A
135 recallrohitg00/agentmemorySearch past session observations and lessons for relevant context. Wrap the memorysmartsearch and memorylessonrecall MCP tools. Command 0 until used 28k A
136 rememberrohitg00/agentmemoryExplicitly save an insight, decision, or learning to agentmemory for future sessions. Wraps the memorysave MCP tool. Command 0 until used 28k A
137 validate-auth-schemakriasoft/react-starter-kitCheck that the Drizzle schema in db/schema/ still satisfies what Better Auth expects. Better Auth derives its required tables from the enabled plugins, so the generated JSON — not the upstream docs — is the source of truth. Command 0 until used 24k A
138 fork-verifier-agentlarksuite/cliYou are a read-only verification subagent spawned to check a design deliverable the main agent just built or edited. Your only job: load that deliverable, verify it, and report a single verdict — done or needswork — back to the main agent. You must not modify, create, or delete any file, edit the source, build, or… Agent 0 until used 17k A
139 fix-sentry-issuecompiler-explorer/compiler-explorerI need you to investigate and fix Sentry issue: $ARGUMENTS. Command 0 until used 19k A
140 builderheygen-com/hyperframesTurn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared… Agent 0 until used 43k A
141 schema-reviewspree/spreeReview a change's database impact and publish it as a visual artifact. Command 0 until used 16k A
142 modulesrun-llama/llama_indexThese guide provide an overview of how to use our agent classes. Agent 0 until used 52k A
143 otel-metricstriggerdotdev/trigger.devGuidelines for creating OpenTelemetry metrics to avoid cardinality issues. Cursor rule 0 until used 16k A
144 test-reviewdatahub-project/datahubYou are an expert DataHub test reviewer. Your role is to evaluate smoke tests and integration tests against established testing standards, identify issues, and provide actionable feedback. Skill 0 until used 13k A
145 react-best-practices-auditvercel-labs/open-agentsAudited against the Vercel React Best Practices (57 rules, 8 categories). Findings are ordered by impact. Agent 0 until used 5.8k A
146 issue-trackeramruthpillai/reactive-resumeIssues and specs for this repo live as GitHub issues. Use the gh CLI for all operations. Agent 0 until used 42k A
147 vision-probe-agentlarksuite/cliYou are a read-only capability probe spawned before a design task tries to read or inspect screenshots. Your only job is to determine whether this Claude Code session's current model/provider can accept image input. Agent 0 until used 17k A
148 model_architecturesaxolotl-ai-cloud/axolotlModel-specific quirks, required settings, and known issues. Check this before debugging training failures on specific model families. Agent 0 until used 12k A
149 Forgedanielmiessler/LifeOSOpenAI-family cross-vendor agent — runs OpenAI's flagship coding model via codex exec (ID resolved from CROSSVENDOR in models.ts, never pinned in prose). TWO MODES set by the spawn prompt. BUILD mode (default) produces production-grade code (writes files, runs tests). AUDIT mode (read-only) is the cross-vendor… Agent 0 until used 19k A
150 ocxlidge-jun/opencodexDrive a running opencodex (ocx) proxy from the CLI — account pools, provider routing, model catalog, usage and cost attribution, request logs, access keys, storage cleanup, and the management API. Use when a task involves controlling or inspecting an opencodex proxy rather than editing the opencodex codebase.… Skill 0 until used 13k A
151 subagentsVoltAgent/voltagentSub-agents are agents that work under a supervisor agent to handle specific tasks. This architecture allows you to create agent workflows where each sub-agent focuses on a specific domain, coordinated by a supervisor. Agent 0 until used 10k A
152 deslopmoeru-ai/airiCheck the diff against main, and remove all AI generated slop introduced in this branch. Command 0 until used 49k A
153 al-folio-v1-migrationalshedivat/al-folioUse this skill when a user asks an agent to migrate an existing customized al-folio fork to v1.x. Skill 0 until used 16k A
154 visualizesemantica-agi/semanticaVisualize the Semantica knowledge graph — topology, centrality, communities, paths, embeddings, decision insights, and temporal evolution. Uses GraphAnalyzer, CentralityCalculator, CommunityDetector, PathFinder, and ContextGraph analytics. Sub-commands: topology, centrality, community, path, decision-graph, insights… Skill 0 until used 11k A
155 AGENTSpatchy631/ai-engineering-hubIn-depth tutorials on LLMs, RAGs and real-world AI agent applications. Agent 0 until used 37k A
156 Maxdanielmiessler/LifeOSAnthropic-family deep-analysis agent — the top-rung scrutiny pass added on top of super-sensitive work (public LifeOS releases, security boundaries, irreversible or publish-bound actions). Pinned to the fable alias, which always resolves to Anthropic's latest top model. Read-only: Edit/Write/NotebookEdit are denied at… Agent 0 until used 19k A
157 al-folio-bootstrapalshedivat/al-folioUse this skill when a user asks an agent to create, configure, or personalize a new al-folio v1.x website. Skill 0 until used 16k A
158 code-stylevercel-labs/open-agentsDetailed coding conventions, tool implementation patterns, and common patterns for the Open Agents codebase. Agent 0 until used 5.8k A
159 e2e-testmaximhq/bifrostSkill "e2e-test" from maximhq/bifrost, covering playwright e2e testing, usage, workflow overview, auto-update workflow (sync mode) and step 0: detect what changed. Skill 0 until used 7.7k A
160 ROCKETRIDE_COMMON_MISTAKESrocketride-org/rocketride-serverA comprehensive guide to avoiding common pitfalls when building RocketRide pipelines and applications. Agent 0 until used 7.5k A
161 basic-agentsJetBrains/koogA basic agent uses a predefined strategy with a simple execution flow that works for most common use cases. It accepts a string input (a question, request, or task description) and sends this input to the configured LLM. The LLM may decide to call provided tools. The agent will execute the tools and send the results… Agent 0 until used 4.5k A
162 ROCKETRIDE_python_APIrocketride-org/rocketride-serverA Python SDK for executing RocketRide pipelines using the Debug Adapter Protocol (DAP). This client provides a simplified interface for connecting to RocketRide DAP servers, executing pipelines, managing data transfer operations, and interacting with AI services. Agent 0 until used 7.5k A
163 cli-anything-generatorHKUDS/CLI-AnythingCLI-Anything generator phase gates and absolute PLUGINROOT resolution. Apply when building, refining, testing, or validating CLI-Anything harnesses, editing agent-harness/, or using /cli-anything commands. Cursor rule 0 until used 49k A
164 indexmuratcankoylan/Agent-Skills-for-Context-EngineeringAgents are reusable AI components with defined capabilities, tools, and instructions. Agent 0 until used 18k A
165 code_reviewFastLED/FastLEDYou are a specialized code review agent for FastLED. Review staged and unstaged changes according to these strict rules. Command 0 until used 7.5k A
166 functional-agentsJetBrains/koogWith functional agents, you implement the logic as a function that handles user input, interacts with LLMs, calls tools if necessary, and produces the final output. Compared to graph-based agents, this usually means faster prototyping with the following downsides. Agent 0 until used 4.5k A
167 database-schemausekaneo/kaneoDatabase schema conventions and patterns using Drizzle ORM and PostgreSQL. Cursor rule 0 until used 8.8k A
168 deployment-devopsusekaneo/kaneoDeployment and DevOps guidelines for Docker Compose and Kubernetes. Cursor rule 0 until used 8.8k A
169 build-agent-empty-input-diagnosisalvinunreal/oh-my-opencode-slimStatus: Resolved for interview injections. Date: 2026-08-10 Related PR: #818 (fix/preset-tui-slash-command) — same root class as the original /preset fix. Suspected sibling bug reported by user: During superpowers / brainstorm skill conversations, when the orchestrator asks for confirmation or work is interrupted… Agent 0 until used 8.5k A
170 codemapalvinunreal/oh-my-opencode-slimDefines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)… Agent 0 until used 8.5k A
171 TEST_LOGagno-agi/agnoAgent "TEST_LOG" from agno-agi/agno, covering testlog and structure validation. Agent 0 until used 42k A
172 deployment-engineerczlonkowski/n8n-mcpUse this agent when you need to set up CI/CD pipelines, containerize applications, configure cloud deployments, or automate infrastructure. This includes creating GitHub Actions workflows, writing Dockerfiles, setting up Kubernetes deployments, implementing infrastructure as code, or establishing deployment… Agent 0 until used 23k A
173 ai_policychromium/chromiumThis policy is for Chromium developers using AI tools to help write code. It is intended to outline expectations around the use of such tools. Agent 0 until used 25k A
174 jesse-strategy-testsjesse-ai/jesseUse when writing or modifying tests for Jesse's backend — especially behavior tied to a strategy (entries/exits, take-profit/stop-loss, position lifecycle hooks, closed-trade metrics). Documents this repo's strategy-driven test pattern: a thin test in tests/testparentstrategy.py that runs singleroutebacktest('Name')… Skill 0 until used 8.4k A
175 project-manager-backlogMrLesk/Backlog.mdUse this agent when you need to manage project tasks using the backlog.md CLI tool. This includes creating new tasks, editing tasks, ensuring tasks follow the proper format and guidelines, breaking down large tasks into atomic units, and maintaining the project's task management workflow. Examples: Context: User wants… Agent 0 until used 6.6k A
176 sdd-applyGentleman-Programming/gentle-aiSkill "sdd-apply" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, purpose, what you receive and execution and persistence contract. Skill 0 until used 6.1k A
177 aptabase-analytics-reportthewh1teagle/vibeExport and analyze Vibe Aptabase analytics for recent time windows or existing CSV exports, with emphasis on failure rates, affected users, app versions, and OS breakdowns. Use when Codex needs to: (1) export recent analytics with scripts/exportanalytics.py, (2) filter an export to the exact last N hours, (3) restrict… Skill 0 until used 7.2k A
178 od-expertyzhao062/pyodAnomaly detection expert backed by PyOD's ADEngine. Drives autonomous detection workflows on tabular, time series, graph, text, and image data: profiling, planning, multi-detector comparison, quality assessment, iteration, and reporting. Encodes deep OD knowledge so non-expert users can run the full workflow without… Skill 0 until used 10.0k A
179 FREE_MCP_SERVERSkyegomez/swarmsA catalog of real, public MCP servers you can plug straight into the Swarms Agent class — most require no authentication, a few use a free-tier API key. Runnable examples live in this folder. Agent 0 until used 7.1k A
180 amplifier-expertmicrosoft/amplifierYou are the authoritative consultant for the complete Amplifier ecosystem. Other agents should consult you for. Agent 0 until used 3.1k A
181 hello-coder-contextiOfficeAI/AionUiYou are a coding agent from the Hello World extension. Agent 0 until used 32k A
182 hello-researcher-contextiOfficeAI/AionUiYou are a research assistant from the Hello World extension. Agent 0 until used 32k A
183 summarizesteipete/summarizeMain command. URL, file, or stdin → clean text → summary. Command 0 until used 6.6k A
184 code_auditTencent/AI-Infra-GuardA static security-audit agent for MCP projects. Static analysis examines source code without running it, focusing on vulnerabilities that could be reached through network inputs. Agent 0 until used 6.1k A
185 vuln_reviewTencent/AI-Infra-GuardA security-review agent that checks vulnerability reports for real, reproducible threats and filters out false positives. A false positive is an alleged problem that is not actually exploitable or harmful in the stated environment. Agent 0 until used 6.1k A
186 seed-architectQ00/ouroborosYou transform interview conversations into immutable Seed specifications - the "constitution" for workflow execution. Agent 0 until used 5.7k A
187 storagekenn-io/agentsviewRead this file before changing SQLite, PostgreSQL, CockroachDB, DuckDB, archive resync, or storage queries. Agent 0 until used 5.6k A
188 zenml-domain-modelszenml-io/zenmlHow to understand, add or modify ZenML domain models. Cursor rule 0 until used 5.6k A
189 zenml-orm-schemazenml-io/zenmlHow to understand, add or update ZenML ORM schemas. Cursor rule 0 until used 5.6k A
190 thunder-deep-reviewthunderbird/thunderboltReviews a pull request, diff, or branch against Thunderbolt's house rules (no any, type-over-interface, arrow fns, const/early-return, no error-swallowing or defensive code, useReducer at 3+ useState, useEffect discipline, route code-splitting, soft-deletes, integration-agnostic logic) and the 80 architecture… Skill 0 until used 4.8k A
191 contextlangchain-ai/langgraphjsAgents often require more than a list of messages to function effectively. They need context. Agent 0 until used 3.2k A
192 memorylangchain-ai/langgraphjsLangGraph supports two types of memory essential for building conversational agents. Agent 0 until used 3.2k A
193 js-error-handler-auditorrivet-dev/actorsUse this agent when you need to audit a JavaScript codebase for unhandled errors in top-level async operations, event handlers, and callback functions. This agent should be used proactively when:\n\n \nContext: User wants to improve error handling across their JavaScript codebase.\nuser: "Can you check if we're… Agent 0 until used 6.1k A
194 daemonsteipete/summarizeManage the local daemon and Chrome Native Messaging bridge used by the Side Panel. Command 0 until used 6.6k A
195 app_layer_rulesModelEngine-Group/nexentApp layer (API) contract for FastAPI endpoints in backend/apps. Parse/validate input, call services, map domain errors to HTTP, return JSONResponse on success. Cursor rule 0 until used 5.8k A
196 literature-reviewerGalaxy-Dawn/claude-scholarUse this agent when the user asks to "conduct literature review", "search for papers", "analyze research papers", "identify research gaps", "review related work", or mentions starting a research project. This agent integrates with Zotero for automated paper collection, organization, and full-text analysis. Examples. Agent 0 until used 5.3k A
197 database_layer_rulesModelEngine-Group/nexentDatabase layer standards for models, CRUD, transactions, and exceptions. Cursor rule 0 until used 5.8k A
198 integration-issue-conventionssuperplanehq/superplaneWhen creating or editing SuperPlane integration issue content (base or component issues), or when working in tmp/integrationspm or integration PM workflow. Cursor rule 0 until used 5.6k A
199 s3-providerskenn-io/agentsviewRead this file before enabling S3 ingest for an agent, changing S3Provider / Source.S3Discovery, or altering S3 discovery, session IDs, temp materialization, or post-fetch hydrate. Agent 0 until used 5.6k A
200 component-example-creatorchakra-ui/arkUse this agent when the user requests examples for a component, asks to add stories to a component, needs documentation examples updated, or mentions creating/updating component demonstrations. Examples:\n\n \nContext: User is working on the Checkbox component and wants to add new usage examples.\nuser: "Can you… Agent 0 until used 5.4k A

Counted with the o200k_base tokenizer at crawl time; mcp, hooks and settings are not measured this way, so they are not ranked here. Two mods per repository at most.